R Notebook

library(readr)
FIFADATABASE <- read_csv2("ultimateData.csv")

Using ',' as decimal and '.' as grouping mark. Use read_delim() for more control.
Parsed with column specification:
cols(
  .default = col_double(),
  short_name = col_character(),
  dob = col_number(),
  nationality = col_character(),
  club_name = col_character(),
  league_name = col_character(),
  team_position = col_character(),
  joined = col_number()
)
See spec(...) for full column specifications.

data(FIFADATABASE)

data set 㤼㸱FIFADATABASE㤼㸲 not found

remove.zero = apply(FIFADATABASE, 1, function(row) all(row !=0 ))
FIFADATABASE[remove.zero,]

na.omit(FIFADATABASE)

#Magassággal kapcsolatos tények

cat("A legmagasabb játékos:",max(FIFADATABASE$height_cm),"cm\n")

A legmagasabb játékos: 206 cm

cat("A legalacsonyabb játékos:",min(FIFADATABASE$height_cm),"cm\n")

A legalacsonyabb játékos: 155 cm

heightHist <-hist(FIFADATABASE$height_cm,main = paste("Histogram of heights"),xlab = "Heights (cm)")

imax <- which.max(heightHist$counts)
cat("A legtöbb játékos (", heightHist$counts[imax] ," db) a ",heightHist$breaks[imax],"-",heightHist$breaks[imax+1]," cm tartományba esik", sep="")

A legtöbb játékos (4817 db) a 175-180 cm tartományba esik

FIFADATABASE.filtered<-FIFADATABASE[which(FIFADATABASE$wage_eur>10000
& FIFADATABASE$wage_eur< 200000),] 

height_cm.wage<-aggregate(FIFADATABASE.filtered$wage_eur, by=list(Height = FIFADATABASE.filtered$height_cm), FUN = mean )

colnames(height_cm.wage) <- c("Height", "Mean of Wage")

barplot(height_cm.wage$`Mean of Wage`,names = height_cm.wage$Height,width = 3,las=2,
        col = NULL,
        horiz = FALSE,
        cex.names = 0.6,
        xlab = "Height(cm)",
        main="Average salary by player's height")

#Top 10 legmagasabb nemzet a FIFA-ban játszó játékosaik alapján

height_cm.nation<-aggregate(FIFADATABASE$height_cm, by=list(Nationality = FIFADATABASE$nationality), FUN = mean )
height_cm.nation <- height_cm.nation[order(height_cm.nation[,2],decreasing = TRUE ),]
height_cm.nation <- height_cm.nation[1:10,]

colnames(height_cm.nation) <- c("Nation", "Mean of height")
height_cm.nation

ylim <- c(0, 1.1*max(height_cm.nation$`Mean of height`))

plot.height<-barplot(height_cm.nation$`Mean of height`,names = height_cm.nation$Nation,width = 3,ylim = ylim,xaxt="n",
        col = NULL,
        horiz = FALSE,
        cex.names = 0.6,
        ylab = "Height(cm)",
        main="Average heights by nations")
rounded.average.height<-round(height_cm.nation$`Mean of height`,digits = 1)

text(x = plot.height, y = height_cm.nation$`Mean of height` ,label = rounded.average.height, pos = 3, cex = 0.8, col = "red")

text(x = plot.height, y = height_cm.nation$`Mean of height` ,label = height_cm.nation$Nation,srt=90, pos = 2, cex = 1, col = "black",adj=2)

#Top 10 legalacsonyabb nemzet a FIFA-ban játszó játékosaik alapján


height_cm.nation<-aggregate(FIFADATABASE$height_cm, by=list(Nationality = FIFADATABASE$nationality), FUN = mean )
height_cm.nation <- height_cm.nation[order(height_cm.nation[,2],decreasing = FALSE ),]
height_cm.nation <- height_cm.nation[1:10,]

colnames(height_cm.nation) <- c("Nation", "Mean of height")
height_cm.nation

ylim <- c(0, 1.1*max(height_cm.nation$`Mean of height`))

plot.height<-barplot(height_cm.nation$`Mean of height`,names = height_cm.nation$Nation,width = 3,ylim = ylim,xaxt="n",
        col = NULL,
        horiz = FALSE,
        cex.names = 0.6,
        ylab = "Height(cm)",
        main="Average heights by nations")
rounded.average.height<-round(height_cm.nation$`Mean of height`,digits = 1)

text(x = plot.height, y = height_cm.nation$`Mean of height` ,label = rounded.average.height, pos = 3, cex = 0.8, col = "red")

text(x = plot.height, y = height_cm.nation$`Mean of height` ,label = height_cm.nation$Nation,srt=90, pos = 2, cex = 1, col = "black",adj=2)

NA
NA
NA

#A clubok melyekben átlagosan a legalacsonyabb játékosok játszanak
height.club<-aggregate(FIFADATABASE$height_cm, by=list(Clubs = FIFADATABASE$club_name), FUN = mean )
height.club <- height.club[order(height.club[,2],decreasing = FALSE ),]
height.club <- height.club[1:10,]

colnames(height.club) <- c("Club", "Mean of height")

height.club

ylim <- c(0, 1.1*max(height.club$`Mean of height`))

plot.height<-barplot(height.club$`Mean of height`,names = height.club$Club,width = 3,ylim = ylim,xaxt="n",
        col = NULL,
        horiz = FALSE,
        cex.names = 0.6,
        ylab = "Height (cm)",
        main="Average heights by clubs")
rounded.average.height<-round(height.club$`Mean of height`,digits = 2)

text(x = plot.height, y = height.club$`Mean of height` ,label = rounded.average.height, pos = 3, cex = 0.8, col = "blue")

text(x = plot.height, y = height.club$`Mean of height` ,label = height.club$Club,srt=90, pos = 2, cex = 1, col = "black",adj=2)

#A clubok melyekben átlagosan a legmagasabb játékosok játszanak
height.club<-aggregate(FIFADATABASE$height_cm, by=list(Clubs = FIFADATABASE$club_name), FUN = mean )
height.club <- height.club[order(height.club[,2],decreasing = TRUE ),]
height.club <- height.club[1:10,]

colnames(height.club) <- c("Club", "Mean of height")

height.club

ylim <- c(0, 1.1*max(height.club$`Mean of height`))

plot.height<-barplot(height.club$`Mean of height`,names = height.club$Club,width = 3,ylim = ylim,xaxt="n",
        col = NULL,
        horiz = FALSE,
        cex.names = 0.6,
        ylab = "Height (cm)",
        main="Average heights by clubs")
rounded.average.height<-round(height.club$`Mean of height`,digits = 2)

text(x = plot.height, y = height.club$`Mean of height` ,label = rounded.average.height, pos = 3, cex = 0.8, col = "blue")

text(x = plot.height, y = height.club$`Mean of height` ,label = height.club$Club,srt=90, pos = 2, cex = 1, col = "black",adj=2)

NA
NA
NA

#Korral kapcsolatos tények

cat("A legidősebb játékos:",max(FIFADATABASE$age),"éves\n")

A legidősebb játékos: 53 éves

cat("A legafiatalabb játékos:",min(FIFADATABASE$age),"éves\n")

A legafiatalabb játékos: 16 éves

agehist<-hist(FIFADATABASE$age,main = paste("Histogram of ages"),xlab = "Ages (year)",xlim = c(15,45))
axis(side = 1,at=seq(10,45,by=5))

cat("A legtöbb játékos (", agehist$counts[imax] ," db) a ",agehist$breaks[imax],"-",agehist$breaks[imax+1]," év tartományba esik", sep="")

A legtöbb játékos (2527 db) a 24-26 év tartományba esik

imax <- which.max(agehist$counts)

wageByAge<-aggregate(FIFADATABASE.filtered$wage_eur, by=list(Age = FIFADATABASE.filtered$age), FUN = mean )

colnames(wageByAge) <- c("Age", "Mean of Wage")

barplot(wageByAge$`Mean of Wage`,names = wageByAge$Age ,width = 3,las=1,
        col = NULL,
        horiz = FALSE,
        cex.names = 0.6,
        xlab = "Age (year)",
        main="Average salary by player's age")

NA
NA

#Top 10 legfiatalabb nemzet a FIFA-ban játszó játékosaik alapján
age.nation<-aggregate(FIFADATABASE$age, by=list(Nationality = FIFADATABASE$nationality), FUN = mean )
age.nation <- age.nation[order(age.nation[,2],decreasing = FALSE ),]
age.nation <- age.nation[1:10,]

colnames(age.nation) <- c("Nation", "Mean of age")

age.nation

ylim <- c(0, 1.1*max(age.nation$`Mean of age`))

plot.age<-barplot(age.nation$`Mean of age`,names = age.nation$Nation,width = 3,ylim = ylim,xaxt="n",
        col = NULL,
        horiz = FALSE,
        cex.names = 0.6,
        ylab = "Age (year)",
        main="Average age by nations")
rounded.average.heights<-round(age.nation$`Mean of age`,digits = 2)

text(x = plot.age, y = age.nation$`Mean of age` ,label = rounded.average.heights, pos = 3, cex = 0.8, col = "red")

text(x = plot.age, y = age.nation$`Mean of age` ,label = age.nation$Nation,srt=90, pos = 2, cex = 1, col = "black",adj=2)

#Top 10 legidősebbb nemzet a FIFA-ban játszó játékosaik alapján
age.nation<-aggregate(FIFADATABASE$age, by=list(Nationality = FIFADATABASE$nationality), FUN = mean )
age.nation <- age.nation[order(age.nation[,2],decreasing = TRUE ),]
age.nation <- age.nation[1:10,]

colnames(age.nation) <- c("Nation", "Mean of age")

palette("default")

age.nation

ylim <- c(0, 1.1*max(age.nation$`Mean of age`))

plot.age<-barplot(age.nation$`Mean of age`,names = age.nation$Nation,width = 3,ylim = ylim,xaxt="n",
        col = NULL,
        horiz = FALSE,
        cex.names = 0.6,
        ylab = "Age (year)",
        main="Average age by nations")
rounded.average.heights<-round(age.nation$`Mean of age`,digits = 2)

text(x = plot.age, y = age.nation$`Mean of age` ,label = rounded.average.heights, pos = 3, cex = 0.8, col = "red")

text(x = plot.age, y = age.nation$`Mean of age` ,label = age.nation$Nation,srt=90, pos = 2, cex = 1, col = "black",adj=2)

NA
NA
NA

#A clubok melyekben átlagosan a legfiatalabb játékosok játszanak
age.club<-aggregate(FIFADATABASE$age, by=list(Clubs = FIFADATABASE$club_name), FUN = mean )
age.club <- age.club[order(age.club[,2],decreasing = FALSE ),]
age.club <- age.club[1:10,]

colnames(age.club) <- c("Club", "Mean of age")

age.club

ylim <- c(0, 1.1*max(age.club$`Mean of age`))

plot.age<-barplot(age.club$`Mean of age`,names = age.club$Club,width = 3,ylim = ylim,xaxt="n",
        col = NULL,
        horiz = FALSE,
        cex.names = 0.6,
        ylab = "Age (year)",
        main="Average age by clubs")
rounded.average.heights<-round(age.club$`Mean of age`,digits = 2)

text(x = plot.age, y = age.club$`Mean of age` ,label = rounded.average.heights, pos = 3, cex = 0.8, col = "blue")

text(x = plot.age, y = age.club$`Mean of age` ,label = age.club$Club,srt=90, pos = 2, cex = 1, col = "black",adj=2)

#A clubok melyekben átlagosan a legidősebb játékosok játszanak
age.club<-aggregate(FIFADATABASE$age, by=list(Clubs = FIFADATABASE$club_name), FUN = mean )
age.club <- age.club[order(age.club[,2],decreasing = TRUE ),]
age.club <- age.club[1:10,]

colnames(age.club) <- c("Club", "Mean of age")

age.club

ylim <- c(0, 1.1*max(age.club$`Mean of age`))

plot.age<-barplot(age.club$`Mean of age`,names = age.club$Club,width = 3,ylim = ylim,xaxt="n",
        col = NULL,
        horiz = FALSE,
        cex.names = 0.6,
        ylab = "Age (year)",
        main="Average age by clubs")
rounded.average.heights<-round(age.club$`Mean of age`,digits = 2)

text(x = plot.age, y = age.club$`Mean of age` ,label = rounded.average.heights, pos = 3, cex = 0.8, col = "blue")

text(x = plot.age, y = age.club$`Mean of age` ,label = age.club$Club,srt=90, pos = 2, cex = 1, col = "black",adj=0.5)

NA
NA

#a top 10 legtöbb játékost a FIFA-ba delegáló ország

different_nations <-unique(FIFADATABASE$nationality)

playersCounted <-table(FIFADATABASE$nationality)
numberOfPlayersByNations <-data.frame(playersCounted)
numberOfPlayersByNations <- numberOfPlayersByNations[order(numberOfPlayersByNations[,2],decreasing = TRUE ),]
numberOfPlayersByNations <- numberOfPlayersByNations[1:10,]

colnames(numberOfPlayersByNations) <- c("Nation", "Number of players")

numberOfPlayersByNations

nations<- unique(numberOfPlayersByNations$Nation)
numbers<-c(numberOfPlayersByNations$`Number of players`)

library(plotly)

package 㤼㸱plotly㤼㸲 was built under R version 4.0.4Loading required package: ggplot2
package 㤼㸱ggplot2㤼㸲 was built under R version 4.0.4
Attaching package: 㤼㸱plotly㤼㸲

The following object is masked from 㤼㸱package:ggplot2㤼㸲:

    last_plot

The following object is masked from 㤼㸱package:stats㤼㸲:

    filter

The following object is masked from 㤼㸱package:graphics㤼㸲:

    layout

pie <- plot_ly(numberOfPlayersByNations, labels = nations, values = numbers, type = 'pie',text=numbers)
pie

NA

#top 20 legjobb átlagfizetésű klub

wage.average.by.clubs<- aggregate(FIFADATABASE.filtered$wage_eur, by=list(Club = FIFADATABASE.filtered$club_name), FUN = mean )
wage.average.by.clubs <- wage.average.by.clubs[order(wage.average.by.clubs[,2],decreasing = TRUE),]

colnames(wage.average.by.clubs) <- c("Club", "Mean of wage by clubs")

ylim <- c(0, 1.2*max(wage.average.by.clubs$`Mean of wage by clubs`))
wage.average.by.clubs <- wage.average.by.clubs[1:20,]

rounded.average.wage<-round(wage.average.by.clubs$`Mean of wage by clubs`,digits = 0)

plot.wage<-barplot(wage.average.by.clubs$`Mean of wage by clubs`,names = wage.average.by.clubs$Club,ylim =ylim,las=2,
        col = 1:30,
        horiz = FALSE,
        cex.names = .6,
        main="Mean of wage by Clubs")

text(x = plot.wage, y = wage.average.by.clubs$`Mean of wage by clubs` ,label = rounded.average.wage, pos = 4, cex = 0.7, 
     col = "black",srt=45)